© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14773
    Prev
    Next
    INDEX
    Explanations

    the word "guard" and its variations, indicating a focus on themes of protection or security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ation
    -0.61
    нг
    -0.60
    т
    -0.58
    PickerController
    -0.58
    proken
    -0.57
    queda
    -0.57
    enumii
    -0.57
    ada
    -0.56
    o
    -0.56
    a
    -0.56
    POSITIVE LOGITS
     $\$
    1.39
    $\$
    1.19
     \$
    1.10
    \$
    0.94
     propOrder
    0.84
    {\$
    0.82
     guard
    0.81
    '},
    0.79
    RegistryLite
    0.79
    )}</
    0.75
    Activations Density 0.088%

    No Known Activations